code-quality
Pass
Audited by Gen Agent Trust Hub on Nov 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns were detected. The skill consists of markdown-based reference material intended to guide an AI agent in performing code reviews. All instructions align with established software engineering best practices for the Java and Spring Boot ecosystems.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze untrusted data in the form of Java code changes and Pull Request diffs, which creates a potential surface for indirect prompt injection. However, as this is the primary intended purpose of the skill and the agent's capabilities are restricted to generating textual review reports, the risk is negligible and consistent with the skill's function. 1. Ingestion points: Java code snippets and PR diffs provided by the user for review. 2. Boundary markers: The skill does not specify delimiters to separate untrusted code from instructions. 3. Capability inventory: The skill provides textual review feedback and does not invoke shell commands, file system writes, or network operations. 4. Sanitization: No explicit filtering or sanitization of input code is performed by the skill instructions.
Audit Metadata